We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative optimization-based attacks, we find defenses relying on this effect can be circumvented. We describe characteristic behaviors of defenses exhibiting the effect, and for each of the three types of obfuscated gradients we discover, we develop attack techniques to overcome it. In a case study, examining non-certified white-box-secure defenses at ICLR 2018, we find obfuscated gradients are a common occurrence, with 7 of 9 defenses relying on obfuscated gradients. Our new attacks successfully circumvent 6 completely, and 1 partially, in the original threat model each paper considers.

Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

Deep learning is at the heart of the current rise of artificial intelligence. In the field of computer vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas, deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently led to a large influx of contributions in this direction. This paper presents the first comprehensive survey on adversarial attacks on deep learning in computer vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks (DNNs) have been recently found vulnerable to well-designed input samples called adversarial examples . Adversarial perturbations are imperceptible to human but can easily fool DNNs in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying DNNs in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for DNNs, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples. In addition, three major challenges in adversarial examples and the potential solutions are discussed.

Adversarial Examples: Attacks and Defenses for Deep Learning

Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful distortions to natural examples. Previous studies to defend against adversarial examples mostly focused on refining the DNN models, but have either shown limited success or required expensive computation. We propose a new strategy, \emph{feature squeezing}, that can be used to harden DNN models by detecting adversarial examples. Feature squeezing reduces the search space available to an adversary by coalescing samples that correspond to many different feature vectors in the original space into a single sample. By comparing a DNN model's prediction on the original input with that on squeezed inputs, feature squeezing detects adversarial examples with high accuracy and few false positives. This paper explores two feature squeezing methods: reducing the color bit depth of each pixel and spatial smoothing. These simple strategies are inexpensive and complementary to other defenses, and can be combined in a joint detection framework to achieve high detection rates against state-of-the-art attacks.

Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks.

Lack of transparency in deep neural networks (DNNs) make them susceptible to backdoor attacks, where hidden associations or triggers override normal classification to produce unexpected results. For example, a model with a backdoor always identifies a face as Bill Gates if a specific symbol is present in the input. Backdoors can stay hidden indefinitely until activated by an input, and present a serious security risk to many security or safety related applications, e.g. biometric authentication systems or self-driving cars. We present the first robust and generalizable detection and mitigation system for DNN backdoor attacks. Our techniques identify backdoors and reconstruct possible triggers. We identify multiple mitigation techniques via input filters, neuron pruning and unlearning. We demonstrate their efficacy via extensive experiments on a variety of DNNs, against two types of backdoor injection methods identified by prior work. Our techniques also prove robust against a number of variants of the backdoor attack.

https://www.computer.org/csdl/pds/api/csdl/proceedings/download-article/19skfH8dcqc/pdf

Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks

Deep learning has shown impressive performance on hard perceptual problems. However, researchers found deep learning systems to be vulnerable to small, specially crafted perturbations that are imperceptible to humans. Such perturbations cause deep learning systems to mis-classify adversarial examples, with potentially disastrous consequences where safety or security is crucial. Prior defenses against adversarial examples either targeted specific attacks or were shown to be ineffective. We propose MagNet, a framework for defending neural network classifiers against adversarial examples. MagNet neither modifies the protected classifier nor requires knowledge of the process for generating adversarial examples. MagNet includes one or more separate detector networks and a reformer network. The detector networks learn to differentiate between normal and adversarial examples by approximating the manifold of normal examples. Since they assume no specific process for generating adversarial examples, they generalize well. The reformer network moves adversarial examples towards the manifold of normal examples, which is effective for correctly classifying adversarial examples with small perturbation. We discuss the intrinsic difficulties in defending against whitebox attack and propose a mechanism to defend against graybox attack. Inspired by the use of randomness in cryptography, we use diversity to strengthen MagNet. We show empirically that MagNet is effective against the most advanced state-of-the-art attacks in blackbox and graybox scenarios without sacrificing false positive rate on normal examples.

MagNet: A Two-Pronged Defense against Adversarial Examples

Deep learning has shown promising results on hard perceptual problems in recent years. However, deep learning systems are found to be vulnerable to small adversarial perturbations that are nearly imperceptible to human. Such specially crafted perturbations cause deep learning systems to output incorrect decisions, with potentially disastrous consequences. These vulnerabilities hinder the deployment of deep learning systems where safety or security is important. Attempts to secure deep learning systems either target specific attacks or have been shown to be ineffective. 
In this paper, we propose MagNet, a framework for defending neural network classifiers against adversarial examples. MagNet does not modify the protected classifier or know the process for generating adversarial examples. MagNet includes one or more separate detector networks and a reformer network. Different from previous work, MagNet learns to differentiate between normal and adversarial examples by approximating the manifold of normal examples. Since it does not rely on any process for generating adversarial examples, it has substantial generalization power. Moreover, MagNet reconstructs adversarial examples by moving them towards the manifold, which is effective for helping classify adversarial examples with small perturbation correctly. We discuss the intrinsic difficulty in defending against whitebox attack and propose a mechanism to defend against graybox attack. Inspired by the use of randomness in cryptography, we propose to use diversity to strengthen MagNet. We show empirically that MagNet is effective against most advanced state-of-the-art attacks in blackbox and graybox scenarios while keeping false positive rate on normal examples very low.

MagNet: a Two-Pronged Defense against Adversarial Examples

Modern browsers implement private mode to protect user privacy. However, they do not agree on what protection private mode should provide. We performed the first study on comparing private modes in popular desktop and mobile browsers and found many inconsistencies between different browsers and between the desktop and mobile versions of the same browser. We show that some inconsistencies result from the tradeoff between security and privacy. However, even if private mode leaks no information about the user, the attacker could still track the user by fingerprinting the browser. Recent work suggested that a browser could report randomized configurations, such as font sizes and installed plugins, to defeat fingerprinting. To show that randomizing configuration reports is insecure, we propose an attack that estimates the true configuration based on statistical methods. We demonstrated that this attack was easy and effective.

Dongyu Meng

Papers

MagNet: A Two-Pronged Defense against Adversarial Examples

MagNet: a Two-Pronged Defense against Adversarial Examples

Evaluating private modes in desktop and mobile browsers and their resistance to fingerprinting